Generative Adversarial Networks-Based Semi-Supervised Learning for Hyperspectral Image Classification

Zhi He,Yiwen Wang,Han Liu,Jie Hu

doi:10.3390/rs9101042

Abstract

Classification of hyperspectral image (HSI) is an important research topic in the remote sensing community. Significant efforts (e.g., deep learning) have been concentrated on this task. However, it is still an open issue to classify the high-dimensional HSI with a limited number of training samples. In this paper, we propose a semi-supervised HSI classification method inspired by the generative adversarial networks (GANs). Unlike the supervised methods, the proposed HSI classification method is semi-supervised, which can make full use of the limited labeled samples as well as the sufficient unlabeled samples. Core ideas of the proposed method are twofold. First, the three-dimensional bilateral filter (3DBF) is adopted to extract the spectral-spatial features by naturally treating the HSI as a volumetric dataset. The spatial information is integrated into the extracted features by 3DBF, which is propitious to the subsequent classification step. Second, GANs are trained on the spectral-spatial features for semi-supervised learning. A GAN contains two neural networks (i.e., generator and discriminator) trained in opposition to one another. The semi-supervised learning is achieved by adding samples from the generator to the features and increasing the dimension of the classifier output. Experimental results obtained on three benchmark HSI datasets have confirmed the effectiveness of the proposed method , especially with a limited number of labeled samples.

Highlights

A hyperspectral image [1,2,3,4] contains hundreds of continuous narrow spectral bands, spanning the visible to infrared spectrum
Based on the above analysis, we show a visual illustration of the semi-supervised hyperspectral classification method by generative adversarial networks (GANs) in Spectral-spatial features of the labeled and unlabeled training samples obtained by the 3DBF
It has been applied to hyperspectral classification and the results have demonstrated the advantage of this graph-based method in semi-supervised classification of the hyperspectral image (HSI)

Summary

Introduction

A hyperspectral image [1,2,3,4] contains hundreds of continuous narrow spectral bands, spanning the visible to infrared spectrum. HSI has played a vital role in many applications, among which classification [5,6,7] is one of the crucial processing steps that has received enormous attention. The foremost task in hyperspectral classification is to train an effective classifier with the given training set from each class. Sufficient training samples are crucial to train a reliable classifier. In reality, it is time-consuming and expensive to obtain a large number of samples with class labels. This difficulty will result in the curse of dimensionality (i.e., Hughes phenomenon) and will induce the risk of overfitting

Methods

Results

Conclusion